© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78450
    Prev
    Next
    INDEX
    Explanations

    never ending or stopping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reinstatement
    -0.89
    Bueno
    -0.82
     reinstated
    -0.78
    albert
    -0.78
     Warenkorb
    -0.72
    怎么样
    -0.72
     solches
    -0.69
    锭
    -0.69
     continuation
    -0.68
    addToCart
    -0.67
    POSITIVE LOGITS
     stop
    1.82
     stops
    1.54
    STOP
    1.52
     STOP
    1.46
     Stop
    1.37
     cease
    1.36
    stop
    1.35
     ever
    1.30
    Stop
    1.24
     stopping
    1.24
    Activations Density 0.042%

    No Known Activations